How can I find hashtags without newline or spaces or tabs just hashtags without url hashtags?
function findHashtags(searchText) {
var regexp = /\#\w\w+\s?/g
result = searchText.match(regexp);
if (result) {
result.map(function(s) { return s.trim() });
console.log(result);
} else {
return false;
}
}
Use \b
instead of \s?
- a word boundary instead of additional whitespace to not capture whitespace. Use \B
(not a word boundary) to separate your url hashtags from urls that end in word characters.
So:
function findHashtags(searchText) {
var regexp = /\B\#\w\w+\b/g
result = searchText.match(regexp);
if (result) {
console.log(result);
} else {
return false;
}
}
Which invoked thusly:
findHashtags("http://www.masrawy.com/Sports/Sports_News/details/2014/9/5/338281#HPOFEATURE\n#ss\nddd\n#ddd jaaja ksks #sfsfsf\n#ggdg#hdhhd")
Then returns:
["#ss", "#ddd", "#sfsfsf", "#ggdg", "#hdhhd"]
Note that this will fail if the url ends in anything but a word character (a-z0-9_
). The only option besides that would be to capture and more effectively trim whitespace:
function findHashtags(searchText) {
var regexp = /(\s|^)\#\w\w+\b/gm
result = searchText.match(regexp);
if (result) {
result = result.map(function(s){ return s.trim();});
console.log(result);
return result;
} else {
return false;
}
}